{"id":415,"date":"2019-09-10T21:36:49","date_gmt":"2019-09-10T12:36:49","guid":{"rendered":"https:\/\/best-biostatistics.com\/toukei-er\/entry\/logistic-regression-analysis-with-titanic-data-in-r\/"},"modified":"2025-02-19T22:25:50","modified_gmt":"2025-02-19T13:25:50","slug":"logistic-regression-analysis-with-titanic-data-in-r","status":"publish","type":"post","link":"https:\/\/best-biostatistics.com\/toukei-er\/entry\/logistic-regression-analysis-with-titanic-data-in-r\/","title":{"rendered":"R \u3067\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u3092\u884c\u3046\u65b9\u6cd5"},"content":{"rendered":"\n

\u30bf\u30a4\u30bf\u30cb\u30c3\u30af\u53f7\u306f\u30011912\u5e744\u670814\u65e5\u306e\u591c\u3001\u6c37\u5c71\u306b\u6fc0\u7a81\u3057\u3001\u5317\u5927\u897f\u6d0b\u306e\u5e95\u306b1,500\u540d\u4ee5\u4e0a\u306e\u547d\u3068\u4e00\u7dd2\u306b\u6c88\u3093\u3060\u3002<\/p>\n\n\n\n

\u4e57\u5ba2\u4e57\u54e1\u306e\u751f\u5b58\u30fb\u6b7b\u4ea1\u306e\u30c7\u30fc\u30bf\u3092\u7528\u3044\u3066\u3001\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u5206\u6790\u3092\u5b9f\u884c\u3057\u3066\u307f\u308b\u3002<\/p>\n\n\n\n\n\n\n\n

\u30bf\u30a4\u30bf\u30cb\u30c3\u30af\u53f7\u306e\u751f\u5b58\u30fb\u6b7b\u4ea1\u30c7\u30fc\u30bf\u306f\u3069\u3053\u306b\u3042\u308b\u306e\u304b\uff1f<\/h2>\n\n\n\n

R \u306f\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u3068\u30c7\u30d5\u30a9\u30eb\u30c8\u3067\u4f7f\u7528\u53ef\u80fd\u306a\u72b6\u614b\u306b\u306a\u3063\u3066\u3044\u308b\u3002<\/p>\n\n\n\n

datasets \u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u6587\u5b57\u901a\u308a Titanic \u3068\u3044\u3046\u540d\u524d\u306e\u30c7\u30fc\u30bf\u3060\u3002<\/p>\n\n\n\n

Titanic \u306e\u5185\u5bb9\u3092\u78ba\u8a8d\u3059\u308b<\/h3>\n\n\n\n

str()\u3067\u5185\u5bb9\u3092\u78ba\u8a8d\u3057\u3066\u307f\u308b\u3002<\/p>\n\n\n\n

str<\/span>(<\/span>Titanic)<\/span>\n<\/code><\/pre>\n\n\n\n
\u901a\u5e38\u306edata frame\u3068\u306f\u7570\u306a\u308b\u69cb\u9020\u306b\u306a\u3063\u3066\u3044\u308b\u3002<\/p>\n\n\n\n
><\/span> str<\/span>(<\/span>Titanic)<\/span>\n'table'<\/span> num [<\/span>1<\/span>:<\/span>4<\/span>,<\/span> 1<\/span>:<\/span>2<\/span>,<\/span> 1<\/span>:<\/span>2<\/span>,<\/span> 1<\/span>:<\/span>2<\/span>]<\/span> 0<\/span> 0<\/span> 35<\/span> 0<\/span> 0<\/span> 0<\/span> 17<\/span> 0<\/span> 118<\/span> 154<\/span> ...\n-<\/span> attr<\/span>(<\/span>*<\/span>,<\/span> \"dimnames\"<\/span>)<\/span>=<\/span>List of 4<\/span>\n..$<\/span> Class   :<\/span> chr [<\/span>1<\/span>:<\/span>4<\/span>]<\/span> \"1st\"<\/span> \"2nd\"<\/span> \"3rd\"<\/span> \"Crew\"<\/span>\n..$<\/span> Sex     :<\/span> chr [<\/span>1<\/span>:<\/span>2<\/span>]<\/span> \"Male\"<\/span> \"Female\"<\/span>\n..$<\/span> Age     :<\/span> chr [<\/span>1<\/span>:<\/span>2<\/span>]<\/span> \"Child\"<\/span> \"Adult\"<\/span>\n..$<\/span> Survived:<\/span> chr [<\/span>1<\/span>:<\/span>2<\/span>]<\/span> \"No\"<\/span> \"Yes\"<\/span>\n<\/code><\/pre>\n\n\n\n
\u30c7\u30fc\u30bf\u81ea\u4f53\u3092\u8868\u793a\u3055\u305b\u3066\u307f\u308b\u3002<\/p>\n\n\n\n
Titanic\n<\/code><\/pre>\n\n\n\n
Child, Adult\u3068Survived Yes, No\u306e4\u3064\u306b\u5206\u304b\u308c\u305fClass\u3068Sex\u306e\u5206\u5272\u8868\u304c\u8868\u793a\u3055\u308c\u305f\u3002<\/p>\n\n\n\n
\u3053\u306e\u3088\u3046\u306a\u5f62\u5f0f\u3067\u683c\u7d0d\u3055\u308c\u3066\u3044\u308b\u3002<\/p>\n\n\n\n
><\/span> Titanic\n,<\/span> ,<\/span> Age =<\/span> Child,<\/span> Survived =<\/span> No\nSex\nClass  Male Female\n1st     0<\/span>      0<\/span>\n2nd     0<\/span>      0<\/span>\n3rd    35<\/span>     17<\/span>\nCrew    0<\/span>      0<\/span>\n,<\/span> ,<\/span> Age =<\/span> Adult,<\/span> Survived =<\/span> No\nSex\nClass  Male Female\n1st   118<\/span>      4<\/span>\n2nd   154<\/span>     13<\/span>\n3rd   387<\/span>     89<\/span>\nCrew  670<\/span>      3<\/span>\n,<\/span> ,<\/span> Age =<\/span> Child,<\/span> Survived =<\/span> Yes\nSex\nClass  Male Female\n1st     5<\/span>      1<\/span>\n2nd    11<\/span>     13<\/span>\n3rd    13<\/span>     14<\/span>\nCrew    0<\/span>      0<\/span>\n,<\/span> ,<\/span> Age =<\/span> Adult,<\/span> Survived =<\/span> Yes\nSex\nClass  Male Female\n1st    57<\/span>    140<\/span>\n2nd    14<\/span>     80<\/span>\n3rd    75<\/span>     76<\/span>\nCrew  192<\/span>     20<\/span>\n<\/code><\/pre>\n\n\n\n
\u901a\u5e38\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u72b6\u306b\u3059\u308b\u306b\u306f\u3001as.data.frame()\u3092\u4f7f\u3046\u3002<\/p>\n\n\n\n
as.data.frame<\/span>(<\/span>Titanic)<\/span>\n<\/code><\/pre>\n\n\n\n
4\u3064\u306e\u5909\u6570\u306e\u7d44\u307f\u5408\u308f\u305b\u3054\u3068\u306e\u4eba\u6570\u3068\u3044\u3046\u30c7\u30fc\u30bf\u306e\u5f62\u306b\u5909\u5f62\u3055\u308c\u305f\u3002<\/p>\n\n\n\n
><\/span> as.data.frame<\/span>(<\/span>Titanic)<\/span>\nClass    Sex   Age Survived Freq\n1<\/span>    1st   Male Child       No    0<\/span>\n2<\/span>    2nd   Male Child       No    0<\/span>\n3<\/span>    3rd   Male Child       No   35<\/span>\n4<\/span>   Crew   Male Child       No    0<\/span>\n5<\/span>    1st Female Child       No    0<\/span>\n6<\/span>    2nd Female Child       No    0<\/span>\n7<\/span>    3rd Female Child       No   17<\/span>\n8<\/span>   Crew Female Child       No    0<\/span>\n9<\/span>    1st   Male Adult       No  118<\/span>\n10<\/span>   2nd   Male Adult       No  154<\/span>\n11<\/span>   3rd   Male Adult       No  387<\/span>\n12<\/span>  Crew   Male Adult       No  670<\/span>\n13<\/span>   1st Female Adult       No    4<\/span>\n14<\/span>   2nd Female Adult       No   13<\/span>\n15<\/span>   3rd Female Adult       No   89<\/span>\n16<\/span>  Crew Female Adult       No    3<\/span>\n17<\/span>   1st   Male Child      Yes    5<\/span>\n18<\/span>   2nd   Male Child      Yes   11<\/span>\n19<\/span>   3rd   Male Child      Yes   13<\/span>\n20<\/span>  Crew   Male Child      Yes    0<\/span>\n21<\/span>   1st Female Child      Yes    1<\/span>\n22<\/span>   2nd Female Child      Yes   13<\/span>\n23<\/span>   3rd Female Child      Yes   14<\/span>\n24<\/span>  Crew Female Child      Yes    0<\/span>\n25<\/span>   1st   Male Adult      Yes   57<\/span>\n26<\/span>   2nd   Male Adult      Yes   14<\/span>\n27<\/span>   3rd   Male Adult      Yes   75<\/span>\n28<\/span>  Crew   Male Adult      Yes  192<\/span>\n29<\/span>   1st Female Adult      Yes  140<\/span>\n30<\/span>   2nd Female Adult      Yes   80<\/span>\n31<\/span>   3rd Female Adult      Yes   76<\/span>\n32<\/span>  Crew Female Adult      Yes   20<\/span>\n<\/code><\/pre>\n\n\n\n
\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u8ee2\u63db\u3057\u305fdat\u3067\u8a08\u7b97\u3057\u3066\u3044\u304f\u3002<\/p>\n\n\n\n
dat <-<\/span> as.data.frame<\/span>(<\/span>Titanic)<\/span>\n<\/code><\/pre>\n\n\n\n
\u6027\u5225\u306e\u76f8\u5bfe\u751f\u5b58\u30aa\u30c3\u30ba\u6bd4\u3092\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u30e2\u30c7\u30eb\u3067\u8a08\u7b97\u3059\u308b<\/h2>\n\n\n\n
\u5358\u5909\u91cf\u306e\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30<\/h3>\n\n\n\n
\u6027\u5225\u3068\u751f\u5b58\u30fb\u6b7b\u4ea1\u3092\u639b\u3051\u5408\u308f\u305b\u305f\u3060\u3051\u306e\u30b7\u30f3\u30d7\u30eb\u306a\u30aa\u30c3\u30ba\u6bd4\u3092\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u3067\u8a08\u7b97\u3057\u3066\u307f\u308b\u3002<\/p>\n\n\n\n
glm()\u3092\u4f7f\u3044\u3001family=binomial\u3068\u3059\u308b\u3002\u300c~\u300d\u306e\u5de6\u306b\u751f\u5b58\u30fb\u6b7b\u4ea1\u306e\u30c7\u30fc\u30bf Survived \u3001\u53f3\u306b\u6027\u5225\u30c7\u30fc\u30bf Sex\u3092\u914d\u7f6e\u3059\u308b\u3002<\/p>\n\n\n\n
\u4eca\u56de\u306e\u30c7\u30fc\u30bf\u306f\u4eba\u6570\u306e\u96c6\u8a08\u30c7\u30fc\u30bf\u306a\u306e\u3067\u3001weights=Freq\u3092\u4ed8\u3051\u52a0\u3048\u308b\u3002<\/p>\n\n\n\n
\u751f\u30c7\u30fc\u30bf\u3067\u306a\u3044\u3068\u304d\u306b\u306f\u3053\u308c\u304c\u5fc5\u8981\u3060\u3002<\/p>\n\n\n\n
logi1 <-<\/span> glm<\/span>(<\/span>Survived~<\/span>Sex,<\/span>weights=<\/span>Freq,<\/span>data=<\/span>dat,<\/span>family=<\/span>binomial)<\/span>\nsummary<\/span>(<\/span>logi1)<\/span>\n<\/code><\/pre>\n\n\n\n
\u7d50\u679c\u306f\u3001log\u30aa\u30c3\u30ba\u306f\u3001\u7537\u6027\u30920\u3068\u3059\u308b\u3068\u3001\u5973\u6027\u306f2.3172\u3068\u8a08\u7b97\u3055\u308c\u305f\u3002<\/p>\n\n\n\n
\u7d71\u8a08\u5b66\u7684\u306b\u6709\u610f\u3067\u3042\u308b\u3002<\/p>\n\n\n\n
><\/span> logi1 <-<\/span> glm<\/span>(<\/span>Survived~<\/span>Sex,<\/span>weights=<\/span>Freq,<\/span>data=<\/span>dat,<\/span>family=<\/span>binomial)<\/span>\n><\/span> summary<\/span>(<\/span>logi1)<\/span>\nCall:<\/span>\nglm<\/span>(<\/span>formula =<\/span> Survived ~<\/span> Sex,<\/span> family =<\/span> binomial,<\/span> data =<\/span> dat,<\/span>\nweights =<\/span> Freq)<\/span>\nDeviance Residuals:<\/span>\nMin       1Q   Median       3Q      Max\n-<\/span>17.869<\/span>   -<\/span>3.455<\/span>    0.000<\/span>    5.969<\/span>   24.405<\/span>\nCoefficients:<\/span>\nEstimate Std. Error z value Pr<\/span>(<\/span>>|<\/span>z|<\/span>)<\/span>\n(<\/span>Intercept)<\/span>  -<\/span>1.3128<\/span>     0.0588<\/span>  -<\/span>22.32<\/span>   <<\/span>2e-16<\/span> ***<\/span>\nSexFemale     2.3172<\/span>     0.1196<\/span>   19.38<\/span>   <<\/span>2e-16<\/span> ***<\/span>\n---<\/span>\nSignif. codes:<\/span>  0<\/span> \u2018***<\/span>\u2019 0.001<\/span> \u2018**<\/span>\u2019 0.01<\/span> \u2018*<\/span>\u2019 0.05<\/span> \u2018.\u2019 0.1<\/span> \u2018 \u2019 1<\/span>\n(<\/span>Dispersion parameter for<\/span> binomial family taken to be 1<\/span>)<\/span>\nNull deviance:<\/span> 2769.5<\/span>  on 23<\/span>  degrees of freedom\nResidual deviance:<\/span> 2335.0<\/span>  on 22<\/span>  degrees of freedom\nAIC:<\/span> 2339<\/span>\nNumber of Fisher Scoring iterations:<\/span> 5<\/span>\n<\/code><\/pre>\n\n\n\n
\u5bfe\u6570\u3092\u771f\u6570\u306b\u5909\u63db\u3057\u305f\u307b\u3046\u304c\u308f\u304b\u308a\u3084\u3059\u3044\u3002<\/p>\n\n\n\n
\u81ea\u524d\u306e\u95a2\u6570 rr.95ci() \u3092\u4f7f\u3046\u3002<\/p>\n\n\n\n
rr.95ci <-<\/span> function<\/span>(<\/span>x){<\/span>\nres <-<\/span> exp<\/span>(<\/span>cbind<\/span>(<\/span>coef<\/span>(<\/span>x),<\/span>confint<\/span>(<\/span>x)))<\/span>\ncolnames<\/span>(<\/span>res)<\/span> <-<\/span> c<\/span>(<\/span>\"RR\"<\/span>,<\/span>\"LL(2.5%)\"<\/span>,<\/span>\"UL(97.5%)\"<\/span>)<\/span>\nround<\/span>(<\/span>res,<\/span>2<\/span>)<\/span>\n}<\/span>\n<\/code><\/pre>\n\n\n\n
rr.95ci \u306f Relative Risk and 95% Confidence Interval\u306e\u7565\u3060\u3002<\/p>\n\n\n\n
rr.95ci<\/span>(<\/span>logi1)<\/span>\n<\/code><\/pre>\n\n\n\n
\u5973\u6027\u306e\u30aa\u30c3\u30ba\u6bd4\u306f\u3001\u7537\u6027\u30921\u3068\u3059\u308b\u3068\u300110.15\u3068\u8a08\u7b97\u3055\u308c\u305f\u3002<\/p>\n\n\n\n
\u305d\u308c\u3060\u3051\u512a\u5148\u3055\u308c\u3066\u52a9\u3051\u3089\u308c\u305f\u3068\u3044\u3046\u7d50\u679c\u3060\u3002<\/p>\n\n\n\n
><\/span> rr.95ci<\/span>(<\/span>logi1)<\/span>\nWaiting for<\/span> profiling to be done...\nRR LL<\/span>(<\/span>2.5<\/span>%)<\/span> UL<\/span>(<\/span>97.5<\/span>%)<\/span>\n(<\/span>Intercept)<\/span>  0.27<\/span>     0.24<\/span>      0.30<\/span>\nSexFemale   10.15<\/span>     8.05<\/span>     12.86<\/span>\n<\/code><\/pre>\n\n\n\n
Fisher Exact Test \u3067\u78ba\u8a8d\u3057\u3066\u307f\u308b<\/h3>\n\n\n\n
2×2\u306e\u5206\u5272\u8868\u306e\u30c7\u30fc\u30bf\u306b\u5bfe\u3057\u3066\u3001Fisher Exact Test \u3092\u5b9f\u65bd\u3057\u3066\u307f\u308b\u3002<\/p>\n\n\n\n
\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u3068\u540c\u69d8\u306e\u7d50\u679c\u306b\u306a\u308b\u304b\u78ba\u8a8d\u3057\u3066\u307f\u305f\u3002<\/p>\n\n\n\n
apply()\u3067\u3001\u6027\u5225\u3068\u751f\u5b58\u30fb\u6b7b\u4ea1\u306e\u30c7\u30fc\u30bf\u306e\u5206\u5272\u8868\u3092\u3001\u4ed6\u306e\u8981\u56e0\u306f\u5408\u8a08\u3059\u308b\u3068\u3044\u3046\u51e6\u7f6e\u3092\u3059\u308b\u3002<\/p>\n\n\n\n
\u305d\u306e\u30c6\u30fc\u30d6\u30eb\u3092\u884c\u5217\u3068\u3057\u3066Fisher Exact Test\u3092\u5b9f\u65bd\u3059\u308b\u3002<\/p>\n\n\n\n
apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>2<\/span>,<\/span>4<\/span>),<\/span>sum)<\/span>\nfisher.test<\/span>(<\/span>apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>2<\/span>,<\/span>4<\/span>),<\/span>sum))<\/span>\n<\/code><\/pre>\n\n\n\n
\u30c6\u30fc\u30d6\u30eb\u306e\u6570\u5024\u3092\u898b\u308c\u3070\u3001\u4e00\u76ee\u77ad\u7136\u3067\u3001\u7537\u6027\u306b\u6bd4\u3079\u5973\u6027\u306e\u307b\u3046\u304c\u751f\u304d\u6b8b\u3063\u3066\u3044\u308b\u3002<\/p>\n\n\n\n
Fisher Exact Test\u306e\u7d50\u679c\u3001\u6027\u5225\u3068\u751f\u5b58\u30fb\u6b7b\u4ea1\u306f\u3001\u7d71\u8a08\u5b66\u7684\u6709\u610f\u306b\u72ec\u7acb\u3067\u3001\u30aa\u30c3\u30ba\u6bd4\u306f10.13\u3067\u3042\u3063\u305f\u3002<\/p>\n\n\n\n
\u3053\u308c\u306f\u5148\u307b\u3069\u306e\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u306e\u7d50\u679c\u3068\u540c\u69d8\u3060\u3002<\/p>\n\n\n\n
><\/span> apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>2<\/span>,<\/span>4<\/span>),<\/span>sum)<\/span>\nSurvived\nSex        No Yes\nMale   1364<\/span> 367<\/span>\nFemale  126<\/span> 344<\/span>\n><\/span> fisher.test<\/span>(<\/span>apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>2<\/span>,<\/span>4<\/span>),<\/span>sum))<\/span>\nFisher's Exact Test for Count Data<\/span>\ndata:  apply(Titanic, c(2, 4), sum)<\/span>\np-value < 2.2e-16<\/span>\nalternative hypothesis: true odds ratio is not equal to 1<\/span>\n95 percent confidence interval:<\/span>\n  7.97665 12.92916<\/span>\nsample estimates:<\/span>\nodds ratio <\/span>\n   10.1319 <\/span>\n<\/code><\/pre>\n\n\n\n
\uff1e\uff1e\u3082\u3046\u7d71\u8a08\u3067\u60a9\u3080\u306e\u306f\u7d42\u308f\u308a\u306b\u3057\u307e\u305b\u3093\u304b\uff1f\u00a0<\/a><\/strong><\/span><\/p>\r\n\"\"<\/a>\r\n
\u21911\u4e07\u4eba\u4ee5\u4e0a\u306e\u533b\u7642\u5f93\u4e8b\u8005\u304c\u8cfc\u8aad\u4e2d<\/span><\/strong><\/span><\/p><\/div>
\u5ba2\u5ba4\u30fb\u6027\u5225\u30fb\u5e74\u9f62\u3092\u52a0\u5473\u3057\u305f\u591a\u91cd\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u30e2\u30c7\u30eb\u3067\u5206\u6790\u3059\u308b<\/h2>\n\n\n\n
\u5ba2\u5ba4 Class\u3001\u6027\u5225 Sex\u3001\u5e74\u9f62 Age\u3092\u540c\u6642\u306b\u6295\u5165\u3057\u305f\u591a\u5909\u91cf\u30e2\u30c7\u30eb\u3067\u5206\u6790\u3057\u3066\u307f\u308b\u3002<\/p>\n\n\n\n
glm()\u306b\u3001family=binomial\u3092\u52a0\u3048\u308b\u306e\u306f\u540c\u69d8\u3002\u300c~\u300d\u306e\u5de6\u306f\u540c\u69d8\u306bSurvived\u3001\u53f3\u306fClass, Sex, Age\u3092\u300c+\u300d\u3067\u3064\u306a\u3044\u3067\u6295\u5165\u3002<\/p>\n\n\n\n
logi2 <-<\/span> glm<\/span>(<\/span>Survived ~<\/span> Class+<\/span>Sex+<\/span>Age,<\/span> weights=<\/span>Freq,<\/span> family=<\/span>binomial,<\/span> data=<\/span>dat)<\/span>\nsummary<\/span>(<\/span>logi2)<\/span>\nrr.95ci<\/span>(<\/span>logi2)<\/span>\n<\/code><\/pre>\n\n\n\n
\u7d50\u679c\u3068\u3057\u3066\u5168\u90e8\u306e\u8aac\u660e\u5909\u6570\u304c\u7d71\u8a08\u5b66\u7684\u6709\u610f\u3067\u3042\u3063\u305f\u3002<\/p>\n\n\n\n
\u4e00\u7b49\u5ba2\u5ba4\u306e\u4e57\u5ba2\u306b\u6bd4\u3079\u3001\u4e8c\u7b49\u3001\u4e09\u7b49\u3001\u4e57\u52d9\u54e1\u306f\u8ab0\u3082\u304c\u751f\u304d\u6b8b\u308c\u306a\u304b\u3063\u305f\u3002<\/p>\n\n\n\n
\u5973\u6027\u306e\u307b\u3046\u304c\u751f\u304d\u6b8b\u3063\u305f\u306e\u306f\u5358\u5909\u91cf\u306e\u7d50\u679c\u3068\u540c\u3058\u3002<\/p>\n\n\n\n
\u5b50\u4f9b\u306b\u6bd4\u3079\u5927\u4eba\u306e\u307b\u3046\u304c\u751f\u304d\u6b8b\u308c\u306a\u304b\u3063\u305f\u3002<\/p>\n\n\n\n
\u5b50\u4f9b\u3092\u512a\u5148\u3057\u305f\u3068\u3044\u3046\u3053\u3068\u3060\u308d\u3046\u3002<\/p>\n\n\n\n
><\/span> summary<\/span>(<\/span>logi2)<\/span>\nCall:<\/span>\nglm<\/span>(<\/span>formula =<\/span> Survived ~<\/span> Class +<\/span> Sex +<\/span> Age,<\/span> family =<\/span> binomial,<\/span>\ndata =<\/span> dat,<\/span> weights =<\/span> Freq)<\/span>\nDeviance Residuals:<\/span>\nMin       1Q   Median       3Q      Max\n-<\/span>18.505<\/span>   -<\/span>4.247<\/span>    0.000<\/span>    4.747<\/span>   23.915<\/span>\nCoefficients:<\/span>\nEstimate Std. Error z value Pr<\/span>(<\/span>>|<\/span>z|<\/span>)<\/span>\n(<\/span>Intercept)<\/span>   0.6853<\/span>     0.2730<\/span>   2.510<\/span>   0.0121<\/span> *<\/span>\nClass2nd     -<\/span>1.0181<\/span>     0.1960<\/span>  -<\/span>5.194<\/span> 2.05e-07<\/span> ***<\/span>\nClass3rd     -<\/span>1.7778<\/span>     0.1716<\/span> -<\/span>10.362<\/span>  <<\/span> 2e-16<\/span> ***<\/span>\nClassCrew    -<\/span>0.8577<\/span>     0.1573<\/span>  -<\/span>5.451<\/span> 5.00e-08<\/span> ***<\/span>\nSexFemale     2.4201<\/span>     0.1404<\/span>  17.236<\/span>  <<\/span> 2e-16<\/span> ***<\/span>\nAgeAdult     -<\/span>1.0615<\/span>     0.2440<\/span>  -<\/span>4.350<\/span> 1.36e-05<\/span> ***<\/span>\n---<\/span>\nSignif. codes:<\/span>  0<\/span> \u2018***<\/span>\u2019 0.001<\/span> \u2018**<\/span>\u2019 0.01<\/span> \u2018*<\/span>\u2019 0.05<\/span> \u2018.\u2019 0.1<\/span> \u2018 \u2019 1<\/span>\n(<\/span>Dispersion parameter for<\/span> binomial family taken to be 1<\/span>)<\/span>\nNull deviance:<\/span> 2769.5<\/span>  on 23<\/span>  degrees of freedom\nResidual deviance:<\/span> 2210.1<\/span>  on 18<\/span>  degrees of freedom\nAIC:<\/span> 2222.1<\/span>\nNumber of Fisher Scoring iterations:<\/span> 5<\/span>\n><\/span> rr.95ci<\/span>(<\/span>logi2)<\/span>\nWaiting for<\/span> profiling to be done...\nRR LL<\/span>(<\/span>2.5<\/span>%)<\/span> UL<\/span>(<\/span>97.5<\/span>%)<\/span>\n(<\/span>Intercept)<\/span>  1.98<\/span>     1.16<\/span>      3.39<\/span>\nClass2nd     0.36<\/span>     0.25<\/span>      0.53<\/span>\nClass3rd     0.17<\/span>     0.12<\/span>      0.24<\/span>\nClassCrew    0.42<\/span>     0.31<\/span>      0.58<\/span>\nSexFemale   11.25<\/span>     8.57<\/span>     14.87<\/span>\nAgeAdult     0.35<\/span>     0.21<\/span>      0.56<\/span>\n<\/code><\/pre>\n\n\n\n
Fisher Exact Test\u3067\u5358\u5909\u91cf\u89e3\u6790\u3082\u3084\u3063\u3066\u307f\u308b<\/h3>\n\n\n\n
\u5927\u4eba\u30fb\u5b50\u4f9b\u3068\u751f\u5b58\u30fb\u6b7b\u4ea1\u306e\u95a2\u4fc2\u3092Fisher Exact Test\u3067\u3082\u5b9f\u884c\u3057\u3066\u307f\u308b\u3002<\/p>\n\n\n\n
apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>3<\/span>,<\/span>4<\/span>),<\/span>sum)<\/span>\nfisher.test<\/span>(<\/span>apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>3<\/span>,<\/span>4<\/span>),<\/span>sum))<\/span>\n<\/code><\/pre>\n\n\n\n
\u5b50\u4f9b\u306e\u307b\u3046\u304c\u751f\u5b58\u3057\u305f\u5272\u5408\u304c\u9ad8\u305d\u3046\u3060\u3002<\/p>\n\n\n\n
><\/span> apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>3<\/span>,<\/span>4<\/span>),<\/span>sum)<\/span>\nSurvived\nAge       No Yes\nChild   52<\/span>  57<\/span>\nAdult 1438<\/span> 654<\/span>\n<\/code><\/pre>\n\n\n\n
\u5927\u4eba\u306e\u307b\u3046\u304c\u7d71\u8a08\u5b66\u7684\u6709\u610f\u306b\u751f\u304d\u6b8b\u308c\u306a\u304f\u3001\u30aa\u30c3\u30ba\u6bd4\u306f0.415\u3067\u3042\u3063\u305f\u3002<\/p>\n\n\n\n
><\/span> fisher.test<\/span>(<\/span>apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>3<\/span>,<\/span>4<\/span>),<\/span>sum))<\/span>\nFisher's Exact Test for Count Data<\/span>\ndata:  apply(Titanic, c(3, 4), sum)<\/span>\np-value = 1.234e-05<\/span>\nalternative hypothesis: true odds ratio is not equal to 1<\/span>\n95 percent confidence interval:<\/span>\n 0.2760923 0.6228448<\/span>\nsample estimates:<\/span>\nodds ratio <\/span>\n 0.4150843 <\/span>\n<\/code><\/pre>\n\n\n\n
\u5ba2\u5ba4\u30af\u30e9\u30b9\u3068\u751f\u5b58\u30fb\u6b7b\u4ea1\u306e\u5358\u5909\u91cf\u89e3\u6790\u306f\u3069\u3046\u3084\u3063\u305f\u3044\u3044\u304b\uff1f<\/h3>\n\n\n\n
Class\u5909\u6570\u306f\u3001\u5ba2\u5ba4\u30af\u30e9\u30b9\u3068\u4e57\u52d9\u54e1\u3092\u5408\u308f\u305b\u3066\u30014\u3064\u306b\u5206\u304b\u308c\u3066\u3044\u308b\u3002<\/p>\n\n\n\n
apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>1<\/span>,<\/span>4<\/span>),<\/span>sum)<\/span>\n<\/code><\/pre>\n\n\n\n
4×2\u306e\u5206\u5272\u8868\u306e\u6642\u306f\u3069\u3046\u3057\u305f\u3089\u3088\u3044\u304b\uff1f<\/p>\n\n\n\n
><\/span> apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>1<\/span>,<\/span>4<\/span>),<\/span>sum)<\/span>\nSurvived\nClass   No Yes\n1st  122<\/span> 203<\/span>\n2nd  167<\/span> 118<\/span>\n3rd  528<\/span> 178<\/span>\nCrew 673<\/span> 212<\/span>\n<\/code><\/pre>\n\n\n\n
epitools \u30d1\u30c3\u30b1\u30fc\u30b8\u3092\u4f7f\u3046\u3002<\/p>\n\n\n\n
Epidemiology (\u75ab\u5b66) \u306e\u30c4\u30fc\u30eb\u304c\u8a70\u307e\u3063\u305f\u30d1\u30c3\u30b1\u30fc\u30b8\u3067\u3042\u308b\u3002<\/p>\n\n\n\n
\u6700\u521d\u306b\u4e00\u56de\u3060\u3051\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u3002<\/p>\n\n\n\n
install.packages<\/span>(<\/span>\"epitools\"<\/span>)<\/span>\n<\/code><\/pre>\n\n\n\n
library()\u3067\u547c\u3073\u51fa\u3059\u3002<\/p>\n\n\n\n
library<\/span>(<\/span>epitools)<\/span>\n<\/code><\/pre>\n\n\n\n
oddsratio()\u3092\u4f7f\u3046\u3068\u3001\u4e00\u884c\u76ee\u3092\u30aa\u30c3\u30ba1\u3068\u3057\u3066\u3001\u4e8c\u884c\u76ee\u4ee5\u964d\u306e\u30aa\u30c3\u30ba\u6bd4\u3092\u8a08\u7b97\u3057\u3066\u304f\u308c\u308b\u3002<\/p>\n\n\n\n
oddsratio<\/span>(<\/span>apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>1<\/span>,<\/span>4<\/span>),<\/span>sum))<\/span>\n<\/code><\/pre>\n\n\n\n
$measure\u306e\u9805\u306b\u7d50\u679c\u304c\u3042\u308a\u3001\u4e00\u7b49\u5ba2\u5ba4\u306e\u4e57\u5ba2\u306b\u6bd4\u3079\u3001\u4e8c\u7b49\u306f0.425\u3001\u4e09\u7b49\u306f0.203\u3001\u4e57\u52d9\u54e1\u306f0.190\u3068\u8a08\u7b97\u3055\u308c\u3066\u3044\u308b\u3002<\/p>\n\n\n\n
\u591a\u5909\u91cf\u30e2\u30c7\u30eb\u4e2d\u306e\u7d50\u679c\u3068\u304a\u304a\u3080\u306d\u4e00\u81f4\u3059\u308b\u3002<\/p>\n\n\n\n
><\/span> oddsratio<\/span>(<\/span>apply<\/span>(<\/span>Titanic,<\/span>c<\/span>(<\/span>1<\/span>,<\/span>4<\/span>),<\/span>sum))<\/span>\n$<\/span>data\nSurvived\nClass     No Yes Total\n1st    122<\/span> 203<\/span>   325<\/span>\n2nd    167<\/span> 118<\/span>   285<\/span>\n3rd    528<\/span> 178<\/span>   706<\/span>\nCrew   673<\/span> 212<\/span>   885<\/span>\nTotal 1490<\/span> 711<\/span>  2201<\/span>\n$<\/span>measure\nodds ratio with 95<\/span>% C.I.\nClass   estimate     lower     upper\n1st  1.0000000<\/span>        NA<\/span>        NA<\/span>\n2nd  0.4254346<\/span> 0.3064855<\/span> 0.5884387<\/span>\n3rd  0.2030991<\/span> 0.1528567<\/span> 0.2686306<\/span>\nCrew 0.1897539<\/span> 0.1441302<\/span> 0.2487196<\/span>\n$<\/span>p.value\ntwo-<\/span>sided\nClass    midp.exact fisher.exact   chi.square\n1st            NA<\/span>           NA<\/span>           NA<\/span>\n2nd  2.029144e-07<\/span> 2.777190e-07<\/span> 2.026267e-07<\/span>\n3rd  0.000000e+00<\/span> 3.675395e-30<\/span> 1.141202e-30<\/span>\nCrew 0.000000e+00<\/span> 1.811851e-34<\/span> 6.880615e-36<\/span>\n$<\/span>correction\n[<\/span>1<\/span>]<\/span> FALSE<\/span>\nattr<\/span>(,<\/span>\"method\"<\/span>)<\/span>\n[<\/span>1<\/span>]<\/span> \"median-unbiased estimate & mid-p exact CI\"<\/span>\n<\/code><\/pre>\n\n\n\n
\u307e\u3068\u3081<\/h2>\n\n\n\n
\u60b2\u5287\u306e\u5927\u4e8b\u6545\u3092\u8d77\u3053\u3057\u305f\u30bf\u30a4\u30bf\u30cb\u30c3\u30af\u53f7\u306e\u751f\u5b58\u30fb\u6b7b\u4ea1\u30c7\u30fc\u30bf\u3092\u3001\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u30e2\u30c7\u30eb\u3067\u5206\u6790\u3057\u3066\u307f\u305f\u3002<\/p>\n\n\n\n
\u591a\u5909\u91cf\u306e\u7d50\u679c\u3060\u3051\u3067\u306a\u304f\u3001\u5358\u5909\u91cf\u306e\u7d50\u679c\u3068\u3082\u7a81\u304d\u5408\u308f\u305b\u306a\u304c\u3089\u3001\u5b9f\u65bd\u3057\u305f\u3002<\/p>\n\n\n\n
\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u30e2\u30c7\u30eb\u306e\u5206\u6790\u65b9\u6cd5\u306f\u3001glm()\u3092\u4f7f\u3044\u3001family=binomial\u3092\u8ffd\u52a0\u3059\u308b\u3002<\/p>\n\n\n\n
\u4eca\u56de\u306e\u3088\u3046\u306b\u96c6\u8a08\u5024\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u5834\u5408\u3001as.data.frame()\u3067\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u5909\u63db\u3057\u3001weights=Freq\uff08Freq\u306f\u983b\u5ea6\u5909\u6570\u306e\u540d\u524d\uff09\u3092\u5fd8\u308c\u306a\u3044\u3088\u3046\u306b\u3059\u308b\u3002<\/p>\n\n\n\n
\u304a\u3059\u3059\u3081\u66f8\u7c4d<\/h2>\n\n\n\n
\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u5206\u6790: SAS\u3092\u5229\u7528\u3057\u305f\u7d71\u8a08\u89e3\u6790\u306e\u5b9f\u969b (\u7d71\u8a08\u30e9\u30a4\u30d6\u30e9\u30ea\u30fc)<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
\u30bf\u30a4\u30bf\u30cb\u30c3\u30af\u53f7\u306f\u30011912\u5e744\u670814\u65e5\u306e\u591c\u3001\u6c37\u5c71\u306b\u6fc0\u7a81\u3057\u3001\u5317\u5927\u897f\u6d0b\u306e\u5e95\u306b1,500\u540d\u4ee5\u4e0a\u306e\u547d\u3068\u4e00\u7dd2\u306b\u6c88\u3093\u3060\u3002 \u4e57\u5ba2\u4e57\u54e1\u306e\u751f\u5b58\u30fb\u6b7b\u4ea1\u306e\u30c7\u30fc\u30bf\u3092\u7528\u3044\u3066\u3001\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u5206\u6790\u3092\u5b9f\u884c\u3057\u3066\u307f\u308b\u3002<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"swell_btn_cv_data":"","_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[5,24],"tags":[],"class_list":["post-415","post","type-post","status-publish","format-standard","hentry","category-r","category-24"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts\/415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/comments?post=415"}],"version-history":[{"count":3,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts\/415\/revisions"}],"predecessor-version":[{"id":3527,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts\/415\/revisions\/3527"}],"wp:attachment":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/media?parent=415"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/categories?post=415"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/tags?post=415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}